AUTOMATIC DETECTION OF MENISCUS TEARS FROM KNEE MRI IMAGES USING DEEP LEARNING: YOLO V8, V9, AND V10 SERIES

Mehmet Ali Şimşek; Ahmet Sertbaş

doi:10.17780/ksujes.1559862

EN TR

AUTOMATIC DETECTION OF MENISCUS TEARS FROM KNEE MRI IMAGES USING DEEP LEARNING: YOLO V8, V9, AND V10 SERIES

Abstract

Meniscal tears are a disease that occurs in the knee joint and negatively affects people's mobility. In this study, the performance of the state-of-the-art (SOTA) YOLO (You Only Look Once) models, in particular YOLOv8l, YOLOv8x, YOLOv9c, YOLOv9e, YOLOv10l, and YOLOv10x, for the detection of meniscal tears was investigated. The algorithms were trained and tested with data from magnetic resonance imaging (MRI). In our study, the YOLOv9e model showed the highest performance and achieved the best results in the training phase with a mAP50 of 0.91807, a precision of 0.87684, a recall of 0.93871 and an F1 score of 0.90672. This study makes a unique contribution to the field with its advanced algorithms and comprehensive performance analysis. The findings show that deep learning algorithms are suitable for clinical use in the automatic detection and localization of meniscal tears. In this way, the possibility of early diagnosis increases, and patients can be directed to the right treatment, preventing joint problems that may occur in the future. In future studies, it is aimed to increase the generalization capabilities of the models with larger data sets and different anatomical structures.

Keywords

DİZ MRI GÖRÜNTÜLERİNDEN MENİSKÜS YIRTIKLARININ DERİN ÖĞRENME İLE OTOMATİK TESPİTİ: YOLO V8, V9 VE V10 SERİLERİ

Öz

Menüsküs yırtıkları diz ekleminde meydana gelen ve insanların hareket kabiliyetlerini olumsuz etkileyen bir hastalıktır. Bu çalışmada, menisküs yırtıklarının tespiti amacıyla YOLOv8l, YOLOv8x, YOLOv9c, YOLOv9e, YOLOv10l ve YOLOv10x gibi son teknoloji YOLO (You Only Look Once) modellerinin performansı incelenmiştir. Algoritmalar, manyetik rezonans görüntüleme (MRG) görüntülerinden elde edilen veriler üzerinde eğitilmiş ve test edilmiştir. Çalışmamızda kullanılan YOLOv9e modeli, eğitim sürecinde elde edilen en iyi sonuçlarda 0,91807 mAP50, 0.87684 Precision, 0.93871 Recall ve 0.90672 F1 Score değerleriyle en yüksek başarıyı göstermiştir. Bu çalışma, kullanılan ileri seviye algoritmalar ve kapsamlı performans analizi ile alanda özgün bir katkı sağlamaktadır. Elde edilen bulgular, derin öğrenme algoritmalarının menisküs yırtıklarının otomatik tespiti ve lokalizasyonunda klinik kullanıma uygun olduğunu göstermektedir. Bu sayede erken teşhis olasılığı artmakta ve hastaların doğru tedaviye yönlendirilmesi sağlanarak ilerleyen dönemde oluşabilecek eklem sorunlarının önüne geçilebilmektedir. İlerleyen çalışmalarda daha geniş veri setleri ve farklı anatomik yapılarla yapılacak araştırmalarla modellerin genelleme yeteneklerinin artırılması hedeflenmektedir.

Anahtar Kelimeler

References

Alif, M. A. R., & Hussain, M. (2024). YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain.
Almajalid, R., Shan, J., Zhang, M., Stonis, G., & Zhang, M. (2019). Knee Bone Segmentation on Three-Dimensional MRI. 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), 1725–1730. IEEE. https://doi.org/10.1109/ICMLA.2019.00280
Bien, N., Rajpurkar, P., Ball, R. L., Irvin, J., Park, A., Jones, E., … Lungren, M. P. (2018). Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet. PLOS Medicine, 15(11), e1002699. https://doi.org/10.1371/journal.pmed.1002699
Bilge, A., Ulusoy, R. G., Üstebay, S., & Öztürk, Ö. (2018). Osteoarthritis. Kafkas Journal of Medical Sciences, 8(50), 133–142. https://doi.org/10.5505/kjms.2016.82653
Botnari, A., Kadar, M., & Patrascu, J. M. (2024). A Comprehensive Evaluation of Deep Learning Models on Knee MRIs for the Diagnosis and Classification of Meniscal Tears: A Systematic Review and Meta-Analysis. Diagnostics, 14(11), 1090. https://doi.org/10.3390/diagnostics14111090
Bryceland, J. K., Powell, A. J., & Nunn, T. (2017). Knee Menisci. CARTILAGE, 8(2), 99–104. https://doi.org/10.1177/1947603516654945
Chou, Y.-T., Lin, C.-T., Chang, T.-A., Wu, Y.-L., Yu, C.-E., Ho, T.-Y., … Kuang-Sheng Lee, O. (2023). Development of artificial intelligence-based clinical decision support system for diagnosis of meniscal injury using magnetic resonance images. Biomedical Signal Processing and Control, 82, 104523. https://doi.org/10.1016/j.bspc.2022.104523
Couteaux, V., Si-Mohamed, S., Nempont, O., Lefevre, T., Popoff, A., Pizaine, G., … Boussel, L. (2019). Automatic Knee Meniscus Tear Detection and Orientation Classification with Mask-RCNN. Diagnostic and Interventional Imaging, 100(4), 235–242. https://doi.org/10.1016/j.diii.2019.03.002

Gaj, S., Yang, M., Nakamura, K., & Li, X. (2020a). Automated cartilage and meniscus segmentation of knee MRI with conditional generative adversarial networks. Magnetic Resonance in Medicine, 84(1), 437–449. https://doi.org/10.1002/mrm.28111
Gaj, S., Yang, M., Nakamura, K., & Li, X. (2020b). Automated Cartilage and Meniscus Segmentation of Knee MRI with Conditional Generative Adversarial Networks. Magnetic Resonance in Medicine, 84(1), 437–449. https://doi.org/10.1002/mrm.28111
Güngör, E., Vehbi, H., Cansın, A., & Ertan, M. B. (2024). Achieving high accuracy in meniscus tear detection using advanced deep learning models with a relatively small data set. Knee Surgery, Sports Traumatology, Arthroscopy. https://doi.org/10.1002/ksa.12369
Harman, F., Selver, M. A., Baris, M. M., Canturk, A., & Oksuz, I. (2023). Deep Learning-Based Meniscus Tear Detection From Accelerated MRI. IEEE Access, 11, 144349–144363. https://doi.org/10.1109/ACCESS.2023.3344456
Hung, T. N. K., Vy, V. P. T., Tri, N. M., Hoang, L. N., Tuan, L. Van, Ho, Q. T., … Kang, J. (2023). Automatic Detection of Meniscus Tears Using Backbone Convolutional Neural Networks on Knee MRI. Journal of Magnetic Resonance Imaging, 57(3), 740–749. https://doi.org/10.1002/jmri.28284
Jocher, G., Chaurasia, A., & Qiu, J. (2023). Yolov8 by Ultralytics.
Li, X., Sun, Y., Jiao, J., Wu, H., Yang, C., & Yang, X. (2021a). Automatic Discoid Lateral Meniscus Diagnosis from Radiographs Based on Image Processing Tools and Machine Learning. Journal of Healthcare Engineering, 2021, 1–7. https://doi.org/10.1155/2021/6662664
Li, X., Sun, Y., Jiao, J., Wu, H., Yang, C., & Yang, X. (2021b). Automatic Discoid Lateral Meniscus Diagnosis from Radiographs Based on Image Processing Tools and Machine Learning. Journal of Healthcare Engineering, 2021, 1–7. https://doi.org/10.1155/2021/6662664
Ma, Y., Qin, Y., Liang, C., Li, X., Li, M., Wang, R., … Jiang, Y. (2023). Visual Cascaded-Progressive Convolutional Neural Network (C-PCNN) for Diagnosis of Meniscus Injury. Diagnostics, 13(12), 2049–2062. https://doi.org/10.3390/diagnostics13122049
Makris, E. A., Hadidi, P., & Athanasiou, K. A. (2011). The knee meniscus: Structure–function, pathophysiology, current repair techniques, and prospects for regeneration. Biomaterials, 32(30), 7411–7431. https://doi.org/10.1016/j.biomaterials.2011.06.037
Ölmez, E., Akdoğan, V., Korkmaz, M., & Er, O. (2020). Automatic Segmentation of Meniscus in Multispectral MRI Using Regions with Convolutional Neural Network (R-CNN). Journal of Digital Imaging, 33(4), 916–929. https://doi.org/10.1007/s10278-020-00329-x
Ozeki, N., Seil, R., Krych, A. J., & Koga, H. (2021). Surgical treatment of complex meniscus tear and disease: state of the art. Journal of ISAKOS, 6(1), 35–45. https://doi.org/10.1136/jisakos-2019-000380
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2015). You Only Look Once: Unified, Real-Time Object Detection.
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779–788.
Roblot, V., Giret, Y., Bou Antoun, M., Morillot, C., Chassin, X., Cotten, A., … Fournier, L. (2019). Artificial Intelligence to Diagnose Meniscus Tears on MRI. Diagnostic and Interventional Imaging, 100(4), 243–249. https://doi.org/10.1016/j.diii.2019.02.007
Sapkota, R., Qureshi, R., Calero, M. F., Badjugar, C., Nepal, U., Poulose, A., … Karkee, M. (2024). YOLOv10 to Its Genesis: A Decadal and Comprehensive Review of The You Only Look Once (YOLO) Series.
Saygili, A., & Albayrak, S. (2017a). Meniscus segmentation and tear detection in the knee MR images by fuzzy c-means method. 2017 25th Signal Processing and Communications Applications Conference (SIU), 1–4.
Saygili, A., & Albayrak, S. (2020). Knee Meniscus Segmentation and Tear Detection from MRI: A Review. Current Medical Imaging Formerly Current Medical Imaging Reviews, 16(1), 2–15. https://doi.org/10.2174/1573405614666181017122109
Saygili, A., & Albayrak, S. (2017b). A new computer-based approach for fully automated segmentation of knee meniscus from magnetic resonance images. Biocybernetics and Biomedical Engineering, 37(3), 432–442. https://doi.org/10.1016/j.bbe.2017.04.008
Sohan, M., Sai Ram, T., & Rami Reddy, Ch. V. (2024). A Review on YOLOv8 and Its Advancements. In Data Intelligence and Cognitive Informatics (pp. 529–545). https://doi.org/10.1007/978-981-99-7962-2_39
Su, Y., Cheng, B., Conference, Y. C.-2023 I. 6th I., & 2023, undefined. (n.d.). Detection and Recognition of Traditional Chinese Medicine Slice Based on YOLOv8. Ieeexplore.Ieee.OrgY Su, B Cheng, Y Cai2023 IEEE 6th International Conference on Electronic Information, 2023•ieeexplore.Ieee.Org. Retrieved from https://ieeexplore.ieee.org/abstract/document/10245026/
Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A. (2023). A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 5(4), 1680–1716. https://doi.org/10.3390/make5040083
Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., & Ding, G. (2024). YOLOv10: Real-Time End-to-End Object Detection.
Wang, C.-Y., & Liao, H.-Y. M. (2024). YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems.
Xiongfeng, T., Yingzhi, L., Xianyue, S., Meng, H., Bo, C., Deming, G., & Yanguo, Q. (2022). Automated detection of knee cystic lesions on magnetic resonance imaging using deep learning. Frontiers in Medicine, 9. https://doi.org/10.3389/fmed.2022.928642
Ying, M., Wang, Y., Yang, K., Wang, H., & Liu, X. (2024). A Deep Learning Knowledge Distillation Framework using Knee MRI and Arthroscopy Data for Meniscus Tear Detection. Frontiers in Bioengineering and Biotechnology, 11. https://doi.org/10.3389/fbioe.2023.1326706
Zhao, R., Zhang, Y., Yaman, B., Lungren, M. P., & Hansen, M. S. (2021). End-to-End AI-based MRI Reconstruction and Lesion Detection Pipeline for Evaluation of Deep Learning Image Reconstruction.
Zhu, K., Chen, Y., Ouyang, X., White, G., & Agam, G. (2022). Fully RNN for knee ligament tear classification and localization in MRI scans. Electronic Imaging, 34(14), 227-1-227–6. https://doi.org/10.2352/EI.2022.34.14.COIMG-227

Details

Primary Language

English

Subjects

Image Processing , Deep Learning , Machine Vision

Journal Section

Research Article

Authors

Mehmet Ali Şimşek ^*
0000-0002-6127-2195
Türkiye

Ahmet Sertbaş
0000-0001-8166-1211
Türkiye

Publication Date

March 3, 2025

Submission Date

October 2, 2024

Acceptance Date

November 8, 2024

Published in Issue

Year 2025 Volume: 28 Number: 1

DOI

https://doi.org/10.17780/ksujes.1559862

IZ

https://izlik.org/JA94WK63ES

Cite

RIS / Bibtex

APA

Şimşek, M. A., & Sertbaş, A. (2025). AUTOMATIC DETECTION OF MENISCUS TEARS FROM KNEE MRI IMAGES USING DEEP LEARNING: YOLO V8, V9, AND V10 SERIES. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 292-308. https://doi.org/10.17780/ksujes.1559862

Cited By

Recognition of Irregularities in Anterior Cruciate Ligament from Magnetic Resonance Images Using Yolo V8

SN Computer Science

https://doi.org/10.1007/s42979-025-04452-w

MOD-YOLOv8: a new YOLOv8-based model for meniscal tear detection in knee MRI

PeerJ Computer Science

https://doi.org/10.7717/peerj-cs.3530